List your company

Context-Aware Question Answering on TriState-Bench Scor

92.5Exact Match (EM)Greedy
-3.721.27546.2571.225Jun 9, 2026

Evaluation results

MethodLinks
GreedyModel=Llama3-8B-Inst2026.0692.595.96
AdaCADModel=Llama3-8B-Inst2026.0691.7595.13
GreedyBackbone=Mistral-7B2026.0691.2594.75
AdaCADBackbone=Mistral-7B2026.069194.25
CADBackbone=Mistral-7B, alpha=0.252026.0690.7594.14
COIECDModel=Llama3-8B-Inst2026.0690.2593.75
GreedyModel=Qwen2.5-7B2026.0689.593.32
ARRBackbone=Mistral-7B2026.068892.73
CoCoAModel=Llama3-8B-Inst2026.0687.2592.06
CADBackbone=Mistral-7B, alpha=0.52026.068791.08
ARRModel=Llama3-8B-Inst2026.0686.7591.75
GreedyModel=Llama2-13B2026.0686.590.79
ARRModel=Qwen2.5-7B2026.0685.7591.09
CADModel=Llama2-13B, alpha=0.252026.0685.2589.85
AdaCADModel=Llama2-13B2026.0685.2589.83
COIECDBackbone=Mistral-7B2026.068589.46
AdaCADModel=Mistral-7B-Inst2026.0684.7589.98
ARRModel=Llama2-13B2026.068489.12
AdaCADModel=Qwen2.5-7B2026.0681.2587.5
GreedyModel=Mistral-7B-Inst2026.068187.37
COIECDModel=Mistral-7B-Inst2026.0680.7587.33
CADModel=Llama2-13B, alpha=0.52026.0680.2585.44
CoCoAModel=Llama2-13B2026.0680.2585.44
COIECDModel=Llama2-13B2026.068084.91
CADBackbone=Mistral-7B, alpha=0.752026.0679.7585.47
AdaCADModel=Llama2-13B-Inst2026.0678.586.7
CADModel=Qwen2.5-7B, alpha=0.252026.0677.584.72
GreedyModel=Llama2-13B-Inst2026.067785.3
ARRModel=Mistral-7B-Inst2026.0676.583.66
CADModel=Mistral-7B-Inst2026.0675.2583.26
ARRBackbone=Llama3-8B2026.067582.68
COIECDModel=Llama2-13B-Inst2026.0674.283.7
CADModel=Llama2-13B, alpha=0.752026.0673.580.52
Simple InterpModel=Qwen2.5-7B, tau=0.752026.067380.68
Simple InterpModel=Llama2-13B, tau=0.752026.0671.575.91
Simple InterpBackbone=Llama3-8B, tau=0.752026.0670.579.25
CADBackbone=Mistral-7B, alpha=1.02026.0670.578.48
CADModel=Llama2-13B, alpha=1.02026.066675.74
Simple InterpBackbone=Mistral-7B, tau=0.752026.066674.97
COIECDModel=Qwen2.5-7B2026.0665.7576.63
CADModel=Llama3-8B-Inst2026.0660.7575.38
GreedyBackbone=Llama3-8B2026.0659.570.79
ARRModel=Llama2-13B-Inst2026.0659.272.8
CADModel=Qwen2.5-7B, alpha=0.52026.0658.571.46
CoCoABackbone=Mistral-7B2026.0655.570.1
AdaCADBackbone=Llama3-8B2026.0651.564.19
CADModel=Llama2-13B-Inst2026.0650.268.8
CADBackbone=Llama3-8B, alpha=0.252026.0644.558
Simple InterpBackbone=Llama3-8B, tau=0.52026.0640.7552.66
CADModel=Qwen2.5-7B, alpha=0.752026.0638.557.62
Simple InterpModel=Llama2-13B, tau=0.52026.0638.543.86
CADBackbone=Llama3-8B, alpha=0.52026.063349.35
Simple InterpModel=Qwen2.5-7B, tau=0.52026.0631.2548.41
CoCoABackbone=Llama3-8B2026.0631.2547.88
COIECDBackbone=Llama3-8B2026.0630.2547.35
CADBackbone=Llama3-8B, alpha=0.752026.0626.7544.72
CoCoAModel=Qwen2.5-7B2026.0626.546.41
CADModel=Qwen2.5-7B, alpha=1.02026.0625.7549.65
CADBackbone=Llama3-8B, alpha=1.02026.0621.7541.07
Simple InterpBackbone=Mistral-7B, tau=0.52026.0620.534.15
Simple InterpModel=Llama2-13B, tau=0.252026.0611.7518.25
CoCoAModel=Llama2-13B-Inst2026.0611.559.8
Simple InterpBackbone=Llama3-8B, tau=0.252026.0610.520.31
CADModel=Qwen2.5-7B-Inst2026.066.527.93
Simple InterpModel=Qwen2.5-7B, tau=0.252026.06620.6
COIECDModel=Qwen2.5-7B-Inst2026.062.525.23
AdaCADModel=Qwen2.5-7B-Inst2026.062.527.64
CoCoAModel=Qwen2.5-7B-Inst2026.062.527.15
Simple InterpBackbone=Mistral-7B, tau=0.252026.062.2514.2
Greedy_no_ctxBackbone=Llama3-8B2026.06211.33
GreedyModel=Qwen2.5-7B-Inst2026.061.2527.81
ARRModel=Qwen2.5-7B-Inst2026.060.7524.44
CoCoAModel=Mistral-7B-Inst2026.060.528.03
Greedy_no_ctxModel=Qwen2.5-7B2026.0608.76
Greedy_no_ctxModel=Llama2-13B2026.0608.16
Greedy_no_ctxBackbone=Mistral-7B2026.0608.96